Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    languages and language-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĭ±æĸĩ
    -0.17
    nger
    -0.15
    ellas
    -0.15
    aneous
    -0.15
    gings
    -0.14
    itionally
    -0.14
    ÅĻe
    -0.14
     norske
    -0.14
    äch
    -0.14
    .ss
    -0.14
    POSITIVE LOGITS
    -speaking
    0.43
    -language
    0.39
     language
    0.30
    -spe
    0.28
    -medium
    0.27
    language
    0.25
     speaking
    0.25
    spe
    0.25
     Language
    0.21
    anguage
    0.20
    Act Density 0.065%

    No Known Activations